Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2768 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.5339. Min Act: -0.1700

Data Index: 7519178 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.5038. Min Act: -0.1700

Data Index: 4066706 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.4380. Min Act: -0.1700

Data Index: 694719 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.3747. Min Act: -0.1700

Data Index: 8438879 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.3905. Min Act: -0.1700

Data Index: 5847281 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.3486. Min Act: -0.1700

Data Index: 8178398 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2913. Min Act: -0.1700

Data Index: 8484093 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2920. Min Act: -0.1700

Data Index: 464630 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2719. Min Act: -0.1700

Data Index: 2525889 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2671. Min Act: -0.1700

Data Index: 5442201 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2663. Min Act: -0.1700

Data Index: 1866141 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2490. Min Act: -0.1700

Data Index: 8301656 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2530. Min Act: -0.1700

Data Index: 4538059 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2716. Min Act: -0.1700

Data Index: 1450582 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2536. Min Act: -0.1700

Data Index: 3087639 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2447. Min Act: -0.1700

Data Index: 6631290 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2469. Min Act: -0.1700

Data Index: 7374697 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2562. Min Act: -0.1700

Data Index: 3753527 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2061. Min Act: -0.1700

Data Index: 139307 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.5339. Min Range: -2.5339

Max Act: 2.2019. Min Act: -0.1700

Data Index: 766598 (Open Web Text)

Max Activating Token Index: 1023